An automatic music production system based on expert audio engineering knowledge is proposed. An expert system based on a probabilistic graphical model is employed to embed professional audio engineering knowledge and infer automatic production decisions based on musical information extracted from audio files. The production pattern, which is represented as probabilistic graphical model, can be ‘learned’ from the operation data of a human audio engineer or manually constructed from domain knowledge. The authors also discuss the real-time implementation of the proposed automatic production system for live mixing application scenarios. Musical event alignment and prediction algorithms are introduced to improve the time synchronization performance of our production model. The authors conclude with performance evaluations and a brief summary.
Authors:
Bocko, Gregory; Bocko, Mark F.; Headlam, Dave; Lundberg, Justin; Ren, Gang
Affiliations:
Dept. of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA; Dept. of Music Theory, University of Rochester, Rochester, NY, USA(See document for exact affiliation information.)
AES Convention:
129 (November 2010)
Paper Number:
8255
Publication Date:
November 4, 2010
Subject:
Signal Analysis and Synthesis
Click to purchase paper as a non-member or you can login as an AES member to see more options.
No AES members have commented on this paper yet.
To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.